Search

Abstract Presently, multi-label classification algorithms are mainly based on positive and negative logical labels, which have achieved good results. However, logical labeling inevitably leads to the label misclassification problem. In addition, missing labels are common in multi-label datasets. Recovering missing labels and constructing soft labels that reflect the mapping relationship between instances and labels is a difficult task. Most existing algorithms can only solve one of these problems. Based on this, this paper proposes a soft-label recover based label-specific features learning (SLR-LSF) to solve the above problems simultaneously. Firstly, the information entropy is used to calculate the confidence matrix between labels, and the membership degree of soft labels is obtained by combining the label density information. Secondly, the membership degree and confidence matrix are combined to construct soft labels, and this process not only solves the problem of missing labels but also obtains soft labels with richer semantic information. Finally, in the process of learning specific label features for soft labels. The local smoothness of the labels learned through stream regularization is complemented by the global label correlation, thus improving the classification performance of the algorithm. To demonstrate the effectiveness of the proposed algorithm, we conduct comprehensive experiments on several datasets.

This work focuses on molecules that are encoded by the major histocompatibility complex (MHC) and that bind self-, foreign- or tumor-derived peptides and display these at the cell surface for recognition by receptors on T lymphocytes (T cell receptors, TCR) and natural killer (NK) cells. The past few decades have accumulated a vast knowledge base of the structures of MHC molecules and the complexes of MHC/TCR with specificity for many different peptides. In recent years, the structures of MHC-I molecules complexed with chaperones that assist in peptide loading have been revealed by X-ray crystallography and cryogenic electron microscopy. These structures have been further studied using mutagenesis, molecular dynamics and NMR approaches. This review summarizes the current structures and dynamic principles that govern peptide exchange as these relate to the process of antigen presentation.

Precise forecasting of cable joint temperature is vital for guaranteeing the safe operation of power supply systems. Nonetheless, the existing predictions are primarily ultra-short-term predictions with brief time steps. This study presents a short-term temperature prediction method based on a work index and an improved Temporal Convolutional Neural Network (TCN). Firstly, the effects of the variables gathered in the monitoring system on the cable joint temperature were examined. To integrate and reconstruct these influencing factors, such as date and human activities, a variable called “work index” was introduced. Subsequently, considering the impact of multidimensional data features, a TCN was used to process long-term historical data effectively and extract potential time series features. Finally, short-term forecasting of cable joint temperature was achieved through multi-feature fusion mapping by using a Back Propagation (BP) neural network. The accuracy of the proposed method was validated using real data from cable joints. The experimental results demonstrated that the proposed method has a mean absolute error (MAE) and a mean squared error (MSE) of 0.929 and 1.529, respectively. It exhibited a 13.3% reduction in MAE and a 12.1% reduction in MSE when compared to state-of-the-art models.

Abstract The COVID-19 pandemic and SARS-CoV-2 variants have dramatically illustrated the need for a better understanding of antigen (epitope)-antibody (paratope) interactions. To gain insight into the immunogenic characteristics of epitopic sites (ES), we systematically investigated the structures of 340 Abs and 83 nanobodies (Nbs) complexed with the Receptor Binding Domain (RBD) of the SARS-CoV-2 spike protein. We identified 23 distinct ES on the RBD surface and determined the frequencies of amino acid usage in the corresponding CDR paratopes. We describe a clustering method for analysis of ES similarities that reveals binding motifs of the paratopes and that provides insights for vaccine design and therapies for SARS-CoV-2, as well as a broader understanding of the structural basis of Ab-protein antigen (Ag) interactions.

The catalytic chaperone tapasin assists peptide loading onto MHC-I molecules for antigen presentation and immune recognition. Here, the authors present crystal structures that provide insights into the molecular mechanism of tapasin-mediated peptide exchange.

Peptide loading of MHC-I molecules plays a critical role in the T cell response to infections and tumors as well as to interactions with inhibitory receptors on natural killer (NK) cells. To facilitate and optimize peptide acquisition, vertebrates have evolved specialized chaperones to stabilize MHC-I molecules during their biosynthesis and to catalyze peptide exchange favoring high affinity or optimal peptides to permit transport to the cell surface where stable peptide/MHC-I (pMHC-I) complexes are displayed and are available for interaction with T cell receptors and any of a host of inhibitory and activating receptors. Although components of the endoplasmic reticulum (ER) resident peptide loading complex (PLC) were identified some 30 years ago, the detailed biophysical parameters that govern peptide selection, binding, and surface display have recently been understood better with advances in structural methods including X-ray crystallography, cryogenic electron microscopy (cryo-EM), and computational modeling. These approaches have provided refined mechanistic illustration of the molecular events involved in the folding of the MHC-I heavy chain, its coordinate glycosylation, assembly with its light chain, β2-microglobulin (β2m), its association with the PLC, and its binding of peptides. Our current view of this important cellular process as it relates to antigen presentation to CD8+ T cells is based on many different approaches: biochemical, genetic, structural, computational, cell biological, and immunological. In this review, taking advantage of recent X-ray and cryo-EM structural evidence and molecular dynamics simulations, examined in the context of past experiments, we attempt a dispassionate evaluation of the details of peptide loading in the MHC-I pathway. By critical evaluation of several decades of investigation, we outline aspects of the peptide loading process that are well-understood and indicate those that demand further detailed investigation. Further studies should contribute not only to basic understanding, but also to applications for immunization and therapy of tumors and infections.

Immune recognition by T lymphocytes and natural killer (NK) cells is in large part dependent on the identification of cell surface MHC molecules bearing peptides generated from either endogenous (MHC I) or exogenous (MHC II) dependent pathways. This review focuses on MHC I molecules that coordinately fold to bind self or foreign peptides for such surface display. Peptide loading occurs in an antigen presentation pathway that includes either the multimolecular peptide loading complex (PLC) or a single chain chaperone/catalyst, TAP binding protein, related, TAPBPR, that mimics a key component of the PLC, tapasin. Recent structural and dynamic studies of TAPBPR reveal details of its function and reflect on mechanisms common to tapasin. Regions of structural conservation among species suggest that TAPBPR and tapasin have evolved to satisfy functional complexities demanded by the enormous polymorphism of MHC I molecules. Recent studies suggest that these two chaperone/catalysts exploit structural flexibility and dynamics to stabilize MHC molecules and facilitate peptide loading.

Peptide loading of MHC-I molecules plays a critical role in the T cell response to infections and tumors as well as to interactions with inhibitory receptors on natural killer (NK) cells. To facilitate and optimize peptide acquisition, vertebrates have evolved specialized chaperones to stabilize MHC-I molecules during their biosynthesis and to catalyze peptide exchange favoring high affinity or optimal peptides to permit transport to the cell surface where stable peptide/MHC-I (pMHC-I) complexes are displayed and are available for interaction with T cell receptors and any of a host of inhibitory and activating receptors. Although components of the endoplasmic reticulum (ER) resident peptide loading complex (PLC) were identified some 30 years ago, the detailed biophysical parameters that govern peptide selection, binding, and surface display have recently been understood better with advances in structural methods including X-ray crystallography, cryogenic electron microscopy (cryo-EM), and computational modeling. These approaches have provided refined mechanistic illustration of the molecular events involved in the folding of the MHC-I heavy chain, its coordinate glycosylation, assembly with its light chain, b2-microglobulin (b2m), its association with the PLC, and its binding of peptides. Our current view of this important cellular process as it relates to antigen presentation to CD8+ T cells is based on many different approaches: biochemical, genetic, structural, computational, cell biological, and immunological. In this review, taking advantage of recent X-ray and cryo-EM structural evidence and molecular dynamics simulations, examined in the context of past experiments, we attempt a dispassionate evaluation of the details of peptide loading in the MHC-I pathway. By critical evaluation of several decades of investigation, we outline aspects of the peptide loading process that are well-understood and indicate those that demand further detailed investigation. Further studies should contribute not only to basic understanding, but also to applications for immunization and therapy of tumors and infections. [ABSTRACT FROM AUTHOR]